Answers are grounded in this paper and cite their sources.
Introduction: Accurate diagnostic tests are essential in clinical and laboratory medicine. Evaluation of diagnostic test performance requires advanced statistical expertise and the use of specialized or proprietary software. The aim of this work is to develop an open-source R Shiny application for facilitating diagnostic test evaluation by integrating statistical rigor with user-friendly interactivity. Materials and methods: web browser. Statistical formulas used to compute diagnostic performance indicators and their confidence intervals were implemented within the R environment to ensure transparency and reproducibility. Results: The developed application provides an interactive interface for importing Excel datasets, setting test variable type, selecting test and reference variables, and specifying disease prevalence. It automatically computes key diagnostic performance indicators, including sensitivity, specificity, predictive values, likelihood ratios, accuracy, the Youden index, and the area under the curve (AUC), along with their 95% confidence intervals. EvalTest also generates confusion matrices, receiver operating characteristic (ROC) curves with confidence bands, and identifies the optimal cutoff for quantitative tests. All numerical and graphical outputs can be exported in suitable formats to facilitate reporting and documentation. Conclusions: EvalTest provides an open and reproducible solution for diagnostic test evaluation by computing and visualizing key performance measures with their confidence intervals, supporting its use in clinical and research settings.
No takes yet. Share an insight, caveat, or question.
Nassim Ayad (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: